TOPIC Toward Human-Level Performance on Face Understanding 
AREA Signal Processing & New Media  
SPEAKER Dr Sun Jian, Principal Researcher, Microsoft Research Asia 
DATE 24 April 2014, Thursday 
TIME 11:00 am to 12:00 pm 
VENUE E2-03-02, Engineering Block E2, Faculty of Engineering, NUS 
FEES No Charge 

SYNOPSIS
Face is arguably the most important visual object in our world. A good understanding of facial image is of great theoretical & practical importance in machine vision and our social world. In the first part of this talk, I will introduce our recent new research progresses on several core sub-problems (detection, alignment, tracking, and recognition) in facial image understanding. Traditionally, these sub-problems were study separately. But we found that the alignment task (locating facial landmarks like nose and eye corners) is the key, which connects other takes. I will talk about how the alignment can greatly improve all other tasks for achieving the state of the arts.
In the second part of the talk, I will present how these research outcomes were applied in Microsoft products, share the lessons I have learned, and discuss remaining challenges in my personal view. See you at the talk!
 

ABOUT THE SPEAKER
Jian was born in Xian (home of Terracotta Army), China, in Oct 1976. He received a BS degree, a MS degree, and a Ph.D degree from Xian Jiaotong University in 1997, 2000 and 2003. He joined Microsoft Research Asia in 2003. His research is in the fields of computer vision and computer graphics, with particular interests in Interactive Compute Vision (user interface + vision), and Internet Compute Vision (large image collection + vision). He is also interested in stereo matching, computational photography, face recognition, and deep learning. He received Best Paper Award for the paper “Single Image Haze Removal Using Dark Channel Prior” at CVPR 2009. In 2010, he was named one of the world''s top 35 young innovators by MIT Technology Review. He served as an area chair for ICCV 2011, CVPR 2013, and as an committee member for Siggraph 2011. Now, he is leading a compute vision team at Microsoft Research Asia. 

REMARKS, IF ANY
 

 | Back to seminar list |

All are welcome to attend these Seminars. Should you have any enquiries, please contact Ms. Lily Png at 6516 6509 or you can e-mail to Ms Lily Png ().